User Preferences for Hybrid Explanations

By Pigi Kouki, J. Schaffer, Jay Pujara, John O'Donovan, Lise Getoor. 2017

76 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Explainable Recommendation: A Survey and New Perspectives (2018, background): “14: A subset of visualizations presented in the user study of hybrid explanations in Kouki et al. [2017].”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, background): “While early recommender system explanation approaches provided a uniform explanation style for single-source collaborative filtering [30], more recent work explores how to derive explanations for recommender systems based on ‘hybrid’ multiple sources [36] and matrix factorisation [61].”
Explore, exploit, and explain: personalizing explainable recommendations with bandits (2018, background): “[13] propose a hybrid recommender system built on a probabilistic programming language and show that explanations improve the user experience of recommender systems.”
Designing Explanation Interfaces for Transparency and Beyond (2019, methodology): “We adopted a hybrid explanation approach [8, 12], which mixed multiple visualizations to explain the details of the recommendation model.”
Personalized Reason Generation for Explainable Song Recommendation (2019, background): “Kouki et al. [32] present explanations such as “Your friend Cindy likes this item” by leveraging information from social networks.”